Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3610 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2393. Min Range: -2.2393

Max Act: 2.1280. Min Act: -0.0000

Data Index: 331877 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 2.2393. Min Range: -2.2393

Max Act: 2.2171. Min Act: -0.0000

Data Index: 410005 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 2.2393. Min Range: -2.2393

Max Act: 2.2393. Min Act: -0.0000

Data Index: 595346 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.7499. Min Act: -0.0000

Data Index: 597011 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.8975. Min Act: -0.0000

Data Index: 495713 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.8184. Min Act: -0.0000

Data Index: 648369 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.7263. Min Act: -0.0000

Data Index: 302836 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.7777. Min Act: -0.0000

Data Index: 857005 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.6915. Min Act: -0.0000

Data Index: 751980 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.5459. Min Act: -0.0000

Data Index: 1012304 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.4859. Min Act: -0.0000

Data Index: 1322733 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.6669. Min Act: -0.0000

Data Index: 571834 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.6474. Min Act: -0.0000

Data Index: 1212316 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.6086. Min Act: -0.0000

Data Index: 398911 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.6949. Min Act: -0.0000

Data Index: 535088 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.6129. Min Act: -0.0000

Data Index: 550613 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.5988. Min Act: -0.0000

Data Index: 1106725 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.5037. Min Act: -0.0000

Data Index: 343302 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.6292. Min Act: -0.0000

Data Index: 1244770 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 2.2393. Min Range: -2.2393

Max Act: 1.6223. Min Act: -0.0000

Data Index: 941602 (C4 (Web Text))

Max Activating Token Index: 202